© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261022
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    せない
    0.44
     circulaire
    0.43
    ོད་
    0.42
     faculté
    0.42
     Vaughn
    0.42
    焚
    0.42
    정과
    0.41
    Escol
    0.41
    궪
    0.41
     órgãos
    0.39
    POSITIVE LOGITS
    itaj
    0.42
    Build
    0.41
    itas
    0.41
     competitive
    0.38
    dirty
    0.38
    isors
    0.38
     शॉर्ट
    0.37
    નાં
    0.36
     equate
    0.35
    oret
    0.35
    Activations Density 0.000%

    No Known Activations